{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"3a76d6254d98","filters":{"venue":"ACM Transactions on Speech and Language Processing"}},"results":[{"id":"W2109163800","doi":"10.1145/1187415.1187417","title":"A statistical model for near-synonym choice","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Synonym (taxonomy); Artificial intelligence; Natural language processing; Task (project management); Context (archaeology); Machine translation; Thesaurus; Mutual information; Information retrieval; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01971804255985616,"gpt":0.3185797563200914,"spread":0.2988617137602353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000425366,0.000192074,0.0001761294,0.0001358429,0.0004433503,0.0003867654,0.0005717867,0.0001192087,0.00001258368],"category_scores_gemma":[0.0001676092,0.0001694326,0.00004658852,0.0003140589,0.00008464247,0.0005752994,0.00002214741,0.0002918141,0.000002838231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004174876,"about_ca_system_score_gemma":0.00010034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004433204,"about_ca_topic_score_gemma":0.00009970817,"domain_scores_codex":[0.9986345,0.00001388799,0.0002354342,0.0004556658,0.0002415595,0.0004189626],"domain_scores_gemma":[0.9989464,0.0003163858,0.00007196594,0.0004111353,0.000102918,0.0001511936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003004011,0.00005880863,0.000008453841,0.00009296165,0.000006819258,0.00002052686,0.001549339,0.00003131428,0.001602214,0.0005060942,0.00002895814,0.9960645],"study_design_scores_gemma":[0.001024877,0.0002427703,0.00008452106,0.0002061457,0.00005419638,0.0001738969,0.0003481439,0.91281,0.06134216,0.02232167,0.0006835413,0.0007080326],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003665246,0.002726696,0.9921808,0.0004304935,0.00004811417,0.0002346301,0.00001777603,0.0005797393,0.0001165606],"genre_scores_gemma":[0.4069453,0.000004842898,0.5922379,0.0004959788,0.00002736153,0.00001753757,0.000003162378,0.00001428731,0.0002536242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9953564,"threshold_uncertainty_score":0.6909263,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091014931","doi":"10.1145/1177055.1177057","title":"Confidence estimation for NLP applications","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Artificial intelligence; Natural language processing; Estimation; Confidence interval; Natural language; Machine learning; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.00987436474930131,"gpt":0.2842979056426198,"spread":0.2744235408933184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001610031,0.0001446771,0.0001243054,0.000151958,0.0003893338,0.0003232013,0.0004842912,0.00008075377,0.000006637809],"category_scores_gemma":[0.00003117941,0.0001327451,0.00004062188,0.0003512303,0.00005292577,0.0006400461,0.00001222096,0.0001480929,0.000004479958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003207166,"about_ca_system_score_gemma":0.00005220659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008095615,"about_ca_topic_score_gemma":0.00002750119,"domain_scores_codex":[0.999042,0.0000141775,0.0001922903,0.0003698835,0.0001655964,0.0002160398],"domain_scores_gemma":[0.9992441,0.0001160421,0.00008975353,0.0003964272,0.0001034865,0.00005018498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006328406,0.00004845936,0.000002585587,0.00009134108,0.000002894358,0.000003011647,0.0002768657,0.00004334034,0.003744363,0.005423162,0.00003135734,0.9903263],"study_design_scores_gemma":[0.0009902022,0.0002115519,0.00005840443,0.0003307959,0.00007103309,0.0002478876,0.0004074427,0.1613738,0.4302529,0.4030198,0.002135058,0.0009010148],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004443829,0.004913214,0.9926556,0.0007532103,0.00002777958,0.0003959314,0.000008731331,0.000648941,0.0001521549],"genre_scores_gemma":[0.4311251,0.000006785866,0.5683165,0.0001623534,0.00003215464,0.0001524924,0.000006679174,0.00000884474,0.0001890756],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9894253,"threshold_uncertainty_score":0.5413188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130998770","doi":"10.1145/1596517.1596518","title":"Extrinsic summarization evaluation","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Sixth Framework Programme","keywords":"Automatic summarization; Computer science; Task (project management); Information retrieval; Audit; Human–computer interaction; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02421893031646663,"gpt":0.2929102533355549,"spread":0.2686913230190883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000240762,0.00008657066,0.0000743233,0.0001199614,0.0001905012,0.0001753455,0.0002264463,0.00004674392,0.00002094664],"category_scores_gemma":[0.0000343554,0.00008184119,0.00002080504,0.0002706592,0.000009944462,0.0005554298,0.00000434935,0.0001115634,0.00000529818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003050285,"about_ca_system_score_gemma":0.00005190429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001322994,"about_ca_topic_score_gemma":0.000009614182,"domain_scores_codex":[0.9991844,0.00003169585,0.0001266187,0.0002657591,0.0002523989,0.0001391285],"domain_scores_gemma":[0.9994972,0.00002264689,0.00004018678,0.0003234005,0.00006668054,0.00004992089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002768269,0.00002653768,0.000008731467,0.00000650536,0.000001674052,0.000003006769,0.001136823,0.0003768467,0.001691835,0.0001115692,0.000001923205,0.9966318],"study_design_scores_gemma":[0.001052171,0.0001651109,0.001575978,0.0001418425,0.00004824456,0.00007983652,0.0007226022,0.9535074,0.03165402,0.01043249,0.0002147411,0.0004055425],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0472578,0.0008914804,0.9497743,0.001021055,0.00006092007,0.0001224506,4.852222e-7,0.000150835,0.0007206403],"genre_scores_gemma":[0.8828462,0.00001771019,0.1165879,0.000399891,0.00003319665,0.000005434797,0.000002088881,0.000003789747,0.0001037413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9962263,"threshold_uncertainty_score":0.3337387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052227241","doi":"10.1145/1289600.1289602","title":"Adaptive text correction with Web-crawled domain-dependent dictionaries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Trigram; Vocabulary; Natural language processing; Domain (mathematical analysis); Information retrieval; Word (group theory); Artificial intelligence; Web page; Crawling; Punctuation; Linguistics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.008003122257323006,"gpt":0.25074320704803,"spread":0.2427400847907071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003984357,0.0002576426,0.0001975287,0.0003369223,0.0006079961,0.0003317864,0.0004739928,0.0001281899,0.00002542252],"category_scores_gemma":[0.00003265876,0.0002031653,0.00004284939,0.0006823508,0.0001259396,0.0009517416,0.00002584086,0.0004818879,0.000007895179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047468,"about_ca_system_score_gemma":0.0001187917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008871258,"about_ca_topic_score_gemma":0.0004279452,"domain_scores_codex":[0.9983808,0.00003648654,0.0002382157,0.0005334304,0.0004264381,0.0003846568],"domain_scores_gemma":[0.9990073,0.0001405535,0.0001294043,0.0004357365,0.0001514523,0.0001355947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001694376,0.0001009761,0.00005989874,0.00003005493,0.00002296609,0.0001331216,0.003438052,0.00001246904,0.004218705,0.0002229158,0.0000232137,0.9915682],"study_design_scores_gemma":[0.006093967,0.003307704,0.001577905,0.002102756,0.0002734762,0.00634604,0.03136396,0.03154594,0.8855633,0.02550241,0.002579642,0.003742931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01491248,0.003459594,0.9790333,0.0004055281,0.0001916869,0.0002120649,0.000003537228,0.0009709857,0.0008108602],"genre_scores_gemma":[0.6213723,0.0000176,0.3778647,0.0002132301,0.00004592296,0.00001435225,0.000001831827,0.00001669287,0.0004533782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9878253,"threshold_uncertainty_score":0.8284841,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}